The Binalyze AIR MCP server enables natural language interaction with digital forensics and incident response capabilities, connecting large language models to Binalyze AIR without requiring complex API knowledge or coding.
# Clone the repository
git clone https://github.com/binalyze/air-mcp
# Change to the project directory
cd air-mcp
# Install dependencies
npm install
# Build the project
npm run build
Add the following to your Claude Desktop configuration file:
{
"mcpServers": {
"air-mcp": {
"command": "npx",
"args": ["-y", "@binalyze/air-mcp"],
"env": {
"AIR_HOST": "your-api-host.com",
"AIR_API_TOKEN": "your-api-token"
}
}
}
}
{
"mcpServers": {
"air-mcp": {
"command": "npx",
"args": ["-y", "@binalyze/air-mcp"],
"env": {
"AIR_HOST": "your-api-host.com",
"AIR_API_TOKEN": "your-api-token"
}
}
}
}
For Claude:
npx -y @smithery/cli@latest install @binalyze/air-mcp --client claude --key {smithery_key}
For Cursor:
npx -y @smithery/cli@latest install @binalyze/air-mcp --client cursor --key {smithery_key}
For Windsurf:
npx -y @smithery/cli@latest install@rapidappio/rapidapp-mcp --client windsurf --key {smithery_key}
For VSCode:
npx -y @smithery/cli@latest install @binalyze/air-mcp --client vscode --key {smithery_key}
Use natural language commands in your MCP client:
List all assets in the system
Get details about asset with ID "abc123"
Get tasks for asset with ID "abc123"
List all acquisition profiles
List all acquisition artifacts
Assign an acquisition task to endpoint 123abc using profile "full" for case "C-2022-0001"
Assign an image acquisition task to endpoint 123abc for volume /dev/sda1 saving to repository 456def
Create an acquisition profile named "My Custom Profile" with windows evidence ["clp"] and linux artifact ["apcl"]
Reboot endpoint 123abc
Shutdown endpoint 123abc
Isolate endpoint 123abc
Unisolate endpoint 123abc
Retrieve logs from endpoint 123abc
Update version for endpoint 123abc
List all organizations
List all cases
Create a new case named "Incident Response"
Update case with ID "C-2022-0003" to have name "Updated Case"
Close case with ID "C-2022-0003"
Acquire baseline for case "C-2022-001" from endpoints ["id1", "id2"]
Compare baselines for endpoint "id1" with task IDs ["task1", "task2"]
Get comparison report for endpoint "id1" and task "task1"
List all policies
Create a policy named "Production Policy" with specific storage settings
List all triage rules
Create triage rule named "My Rule"
Validate triage rule syntax
List repositories
Create SMB repository with name "My SMB Repository"
Create SFTP repository with name "My SFTP Repository"
Create Azure Storage repository with name "My Azure Storage Repository"
Create a new Amazon S3 repository
Add tags ["tag1", "tag2"] to asset with ID "endpoint-id"
Remove tags ["tag1"] from asset with ID "endpoint-id"
Create an auto asset tag named "Web Server"
List all auto asset tag rules
Download PPC file for endpoint "ep-1" and task "task-1"
Download task report for endpoint "123" and task "456"
Export cases data
Export notes for case with ID "case123"
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "air-mcp" '{"command":"npx","args":["-y","@binalyze/air-mcp"],"env":{"AIR_HOST":"your-api-host.com","AIR_API_TOKEN":"your-api-token"}}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"air-mcp": {
"command": "npx",
"args": [
"-y",
"@binalyze/air-mcp"
],
"env": {
"AIR_HOST": "your-api-host.com",
"AIR_API_TOKEN": "your-api-token"
}
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"air-mcp": {
"command": "npx",
"args": [
"-y",
"@binalyze/air-mcp"
],
"env": {
"AIR_HOST": "your-api-host.com",
"AIR_API_TOKEN": "your-api-token"
}
}
}
}
3. Restart Claude Desktop for the changes to take effect